Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2291 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.6755. Min Act: -0.1700
Data Index: 103483 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.6755. Min Act: -0.1700
Data Index: 1548389 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.6130. Min Act: -0.1700
Data Index: 1461350 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.3943. Min Act: -0.1700
Data Index: 8700447 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.3943. Min Act: -0.1700
Data Index: 3203712 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.3005. Min Act: -0.1700
Data Index: 4039747 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2693. Min Act: -0.1700
Data Index: 3733606 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2693. Min Act: -0.1700
Data Index: 8819893 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2693. Min Act: -0.1700
Data Index: 7868896 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2693. Min Act: -0.1700
Data Index: 4801540 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2068. Min Act: -0.1700
Data Index: 5416086 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2380. Min Act: -0.1700
Data Index: 743876 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2380. Min Act: -0.1700
Data Index: 6139361 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2380. Min Act: -0.1700
Data Index: 1974961 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2068. Min Act: -0.1700
Data Index: 1813132 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.1755. Min Act: -0.1700
Data Index: 6479063 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.2068. Min Act: -0.1700
Data Index: 6824255 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.1443. Min Act: -0.1700
Data Index: 5925244 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.1443. Min Act: -0.1700
Data Index: 2280717 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6755. Min Range: -7.6755
Max Act: 7.1443. Min Act: -0.1700
Data Index: 3469055 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19